{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T10:29:39Z","timestamp":1769077779265,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096353","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":7,"title":["VarietySound: Timbre-Controllable Video to Sound Generation Via Unsupervised Information Disentanglement"],"prefix":"10.1109","author":[{"given":"Chenye","family":"Cui","sequence":"first","affiliation":[{"name":"Zhejiang University"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Yi","family":"Ren","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Jinglin","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Rongjie","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Feiyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]},{"given":"Zhefeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Cloud"}]},{"given":"Baoxing","family":"Huai","sequence":"additional","affiliation":[{"name":"Huawei Cloud"}]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00374"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11024-6_43"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3177894"},{"key":"ref6","article-title":"Taming visually guided sound generation","volume-title":"British Machine Vision Conference (BMVC)","author":"Iashin"},{"key":"ref7","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref8","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref9","first-page":"4402","article-title":"Disentangling disentanglement in variational autoencoders","volume-title":"International Conference on Machine Learning","author":"Mathieu"},{"key":"ref10","article-title":"Learning to decompose and disentangle representations for video prediction","volume":"31","author":"Hsieh","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632676"},{"key":"ref12","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","volume":"29","author":"Aytar","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref16","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/620"},{"key":"ref18","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe"},{"key":"ref19","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref20","article-title":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096353.pdf?arnumber=10096353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T04:36:29Z","timestamp":1712982989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096353","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}